Malicious Javascript Detection based on Clustering Techniques

Malicious JavaScript code is still a problem for website and web users. The complication and equivocation of this code make the detection which is based on signatures of antivirus programs becomes ineffective. So far, the alternative methods using machine learning have achieved encouraging results, and have detected malicious JavaScript code with high accuracy. However, according to the supervised learning method, the models, which are introduced, depend on the number of labeled symbols and require significant computational resources to activate. The rapid growth of malicious JavaScript is a real challenge to the solutions based on supervised learning due to the lacking of experience in detecting new forms of malicious JavaScript code. In this paper, we deal with the challenge by the method of detecting malicious JavaScript based on clustering techniques. The known symbols that will be analyzed, the characteristics which are extracted, and a detection processing technique applied on output clusters are included in the model. This method is not computationally complicated, as well as the typical case experiments gave positive results; specifically, it has detected new forms of malicious JavaScript code.

Deteksi dan Pengenalan Objek Dengan Model Machine Learning: Model Yolo

Object recognition and detection have been in request by numerous parties since Computer Vision innovation within the 1960s, both within the industrial and medical area. Since then, many studies have focused on object recognition and detection with various types of algorithm models that can recognize and detect objects in an image. However, not all of these algorithm models are efficient and effective in their application. Most of the previous algorithm models have a relatively high level of complexity. Here, the author tries to explain and introduce the YOLO (You only look once) algorithm model, which has a high enough image detection processing speed capability and accuracy that can compete with the previous algorithm models. There are several advantages and disadvantages of each version made, which are explained in the discussion section.

A Case Study of Whistle Detection and Localization for Humpback Dolphins in Taiwan

In recent years, Taiwan’s government has focused on policies regarding offshore wind farming near the Indo-Pacific humpback dolphin habitat, where marine mammal observation is a critical consideration. The present research developed an algorithm called National Taiwan University Passive Acoustic Monitoring (NTU_PAM) to assist marine mammal observers (MMOs). The algorithm performs whistle detection processing and whistle localization. Whistle detection processing is based on image processing and whistle feature extraction; whistle localization is based on the time difference of arrival (TDOA) method. To test the whistle detection performance, we used the same data to compare NTU_PAM and the widely used software PAMGuard. To test whistle localization, we designed a real field experiment where a sound source projected simulated whistles, which were then recorded by several hydrophone stations. The data were analyzed to locate the moving path of the source. The results show that localization accuracy was higher when the sound source position was in the detection region composed of hydrophone stations. This paper provides a method for MMOs to conveniently observe the migration path and population dynamics of cetaceans without ecological disturbance.

Get HyP3! SAR processing for everyone

<p>Synthetic Aperture Radar (SAR), with its capability of imaging day or night, ability to penetrate dense cloud cover, and suitability for interferometry, is a robust dataset for event/change monitoring. SAR data can be used to inform decision makers dealing with natural and anthropogenic hazards such as floods, earthquakes, deforestation and glacier movement. However, SAR data has only recently become freely available with global coverage, and requires complex processing with specialized software to generate analysis-ready datasets. Furthermore, processing SAR is often resource-intensive, in terms of computing power and memory, and the sheer volume of data available for processing can be overwhelming. For example, ESA's Sentinel-1 has produced ~10PB of data since launch in 2014. Even subsetting the data to a small scientific area of interest can result in many thousands of scenes, which must be processed into an analysis-ready format.</p><p>The Alaska Satellite Facility (ASF) Hybrid Pluggable Processing Pipeline (HyP3), which is now out of beta and available to the public, provides custom, on-demand processing of Sentinel-1 SAR data at no cost to users. HyP3 is integrated directly into Vertex, ASF's primary data discovery tool, so users can easily select an area of interest on the Earth, find available SAR products, and click a button to send them (individually, or as a batch) to HyP3 for Radiometric Terrain Correction (RTC), Interferometric SAR (InSAR), or Change Detection processing. Processing leverages AWS cloud computing and is done in parallel for rapid product generation. Each process provides options to customize the processing and final output products, and provides metadata-rich, analysis-ready final products to users.</p><p>In addition to the Vertex user interface, HyP3 provides a RESTful API and a python software developers kit (SDK) to allow programmatic access and the ability to build HyP3 into user workflows. HyP3 is open source and designed to allow users to develop new processing plugins or stand up their own custom processing pipeline.</p><p>We will present an overview of using HyP3, both inside Vertex and programmatically, and the available output products. We will demonstrate using HyP3 to investigate the consequences of natural hazards and very briefly discuss the technologies and software design principles used in the development of HyP3 and how users could contribute new plugins, or stand up their own custom processing pipeline.</p>

SENTINEL-1 AND SENTINEL-2 TIME SERIES PROCESSING CHAINS FOR CYCLONE IMPACT MONITORING IN SOUTH WEST INDIAN OCEAN

Monitoring the spatial footprint of cyclone impacts by remote sensing offers great potential for assessing the extent of damage and monitoring the resilience of the affected territories. For this purpose, as part of the Renovrisk-Impact project, we have developed two change detection processing chains based on optical (Sentinel-2) and SAR (Sentinel-1) data. These chains have been used to track different events in different regions of the world. In this article we focus on two study sites in Madagascar: the city of Miandrivazo, which was heavily affected by severe rainfall from Cyclone AVA in January 2018, and more recently the town of Marovoay which suffered a major disaster following the passage of tropical storm DIANE in January 2020. The obtained results were evaluated and compared with the Copernicus Emergency Mapping Service product, showing good consistency with this product and between them. These results confirm the potential of these Sentinel data and the developed processing chains for monitoring the impacts of cyclones, but also open up prospects for longer-term monitoring.

The Swedish National Seismic Network

<p>The Swedish National Seismic Network (SNSN) is operating 69 broadband stations in a latitude range from about N55.5 to N68.5 deg. The southern and northern parts of Sweden are covered more or less evenly with stations having about 100km interstation distances. In the center, between latitudes N61 - N65 deg the stations are situated in a band of about 100 km width following the coast of the Bothnian Sea. The maintenance of this large and distributed network - parts of it in Arctic environment - is challenging. All stations are recording at 100 samples per second and are sending continuous data in near real-time to the SNSN centre at Uppsala University. Seismic data are shared via seedlink directly with seismological institutes in the neighbouring countries, and a subset of the network is made available at ORFEUS. The density, spatial distribution and data avalability of the network allow the production of  a reviewed seismic bulletin with a magnitude completeness down to 0.5. We are currently running several independent automatic processing systems at SNSN: Seiscomp3, Earthworm, SIL/MSIL and an in-house developed waveform-backpropagation algorithm. The SIL system was put in operation 1990 and was originally designed to work decentralized (i.e. phase detection processing at each station computer) and to work with segmented data, suitable for a network with narrow communication bandwidth. SIL was further developed into a version called MSIL, which now performs all steps (detection, associaton and localization) centrally. This not only facilitates station and software maintenance, but also reduces the number of potential points of failure, thereby increasing the data acquisition and processing performance. All the automatic systems are set up for regional and local monitoring. Solutions obtained by the Seiscomp3 and Earthworm system are consistent in location and magnitude for more than 90% of the detected events. The SIL/MSIL and the backpropagation system are targeted to weaker events and they provide additional seismic event locations, but also more spurious events. The current setup of several automatic systems provides operational redundancy and it increases the confidence in the automatic solutions (when detected by more than one system). Eventually we are going to merge the automatic solutions of all systems into one automatic bulletin in order to decrease the workload for analyst review.</p>